Robots That Can See: Leveraging Human Pose for Trajectory Prediction

TL;DR

This paper introduces a Transformer-based model that predicts human trajectories in dynamic environments using sensory data, improving safety and navigation for robots by capturing uncertainty and leveraging skeletal pose information.

Contribution

The work presents a novel Transformer architecture for trajectory prediction that incorporates 3D skeletal keypoints and head orientations, achieving state-of-the-art results and addressing data limitations.

Findings

State-of-the-art prediction accuracy on benchmarks

3D skeletal poses reduce prediction errors in limited data scenarios

Model effectively captures uncertainty in human motion trajectories

Abstract

Anticipating the motion of all humans in dynamic environments such as homes and offices is critical to enable safe and effective robot navigation. Such spaces remain challenging as humans do not follow strict rules of motion and there are often multiple occluded entry points such as corners and doors that create opportunities for sudden encounters. In this work, we present a Transformer based architecture to predict human future trajectories in human-centric environments from input features including human positions, head orientations, and 3D skeletal keypoints from onboard in-the-wild sensory information. The resulting model captures the inherent uncertainty for future human trajectory prediction and achieves state-of-the-art performance on common prediction benchmarks and a human tracking dataset captured from a mobile robot adapted for the prediction task. Furthermore, we identify new agents with limited historical data as a major contributor to error and demonstrate the complementary nature of 3D skeletal poses in reducing prediction error in such challenging scenarios.